@article{helixpipeefficientdistributedtrainingofl,
  title = {HelixPipe: Efficient Distributed Training of Long Sequence Transformers with Attention Parallel Pipeline Parallelism},
  author = {Geng Zhang and Shenggan Cheng and Xuanlei Zhao and Ziming Liu and Yang You},
  year = {2025},
  eprint = {2507.00394},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2507.00394},
}